Get all the cards for an account holder
AI agents call cards_list to retrieve information from Starling Bank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a list of cards associated with an account, which is a read-only operation that queries data without side effects. However, the severity is elevated to medium rather than low because card information is sensitive financial data that could enable fraud or identity theft if exposed to an unauthorized agent, even though the tool itself performs no destructive or financial actions.
From the tool's definition Tool name 'cards_list' and description 'Get all the cards for an account holder' indicate data retrieval with no modification capability.
Attacks that exploit this kind of access
Get all the cards for an account holder. It is categorised as a Read tool in the Starling Bank MCP Server, which means it retrieves data without modifying state.
Register the Starling Bank MCP server in PolicyLayer and add a rule for cards_list: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Starling Bank. Nothing to install.
cards_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cards_list rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for cards_list. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
cards_list is provided by the Starling Bank MCP server (starling-bank-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →